Search results

The purpose of this paper is to enhance the performance of spammer identification problem in online social networks. Hyperparameter tuning has been performed by researchers in the past to enhance the performance of classifiers. The AdaBoost algorithm belongs to a class of ensemble classifiers and is widely applied in binary classification problems. A single algorithm may not yield accurate results. However, an ensemble of classifiers built from multiple models has been successfully applied to solve many classification tasks. The search space to find an optimal set of parametric values is vast and so enumerating all possible combinations is not feasible. Hence, a hybrid modified whale optimization algorithm for spam profile detection (MWOA-SPD) model is proposed to find optimal values for these parameters.

In this work, the hyperparameters of AdaBoost are fine-tuned to find its application to identify spammers in social networks. AdaBoost algorithm linearly combines several weak classifiers to produce a stronger one. The proposed MWOA-SPD model hybridizes the whale optimization algorithm and salp swarm algorithm.

The technique is applied to a manually constructed Twitter data set. It is compared with the existing optimization and hyperparameter tuning methods. The results indicate that the proposed method outperforms the existing techniques in terms of accuracy and computational efficiency.

The proposed method reduces the server load by excluding complex features retaining only the lightweight features. It aids in identifying the spammers at an earlier stage thereby offering users a propitious environment.

The primary objective of the study is to enhance the accuracy and efficiency of assessing the proliferation index in cancer cells, specifically focusing on the role of Ki-67. The purpose is to address the limitations of traditional visual assessments conducted by pathologists by integrating AI technologies, particularly deep learning. By accurately computing the percentage of Ki-67-labeled cells, the research aims to streamline the diagnostic process, reduce subjectivity and contribute to the advancement of diagnostic precision in pathological anatomy.

The research employs a methodological approach that integrates Ki-67, a non-histone nuclear protein, as a vital biomarker for assessing the proliferative status of cancer cells. Given the challenges associated with traditional visual assessments by pathologists, including inter- and intra-observer variability and time-consuming efforts, the study adopts a novel methodology leveraging artificial intelligence (AI) solutions. Deep learning is applied to precisely calculate the percentage of Ki-67-labeled cells. The process involves pathologists delineating the tumor area at x40 magnification, enabling the segmentation of various cell types (positive, negative and tumor-infiltrating lymphocytes). The subsequent percentage calculation enhances efficiency and minimizes subjectivity in the diagnostic process.

Despite inherent errors, the research findings indicate that the model surpasses existing benchmarks, showcasing superior accuracy in terms of average error measurement. The comparison with diverse datasets and benchmarking against pathologists’ diagnoses contributes empirical evidence to support the effectiveness of the AI-based model in accurately computing the percentage of Ki-67-labeled cells. These findings signify a noteworthy advancement in diagnostic methodologies and reinforce the potential of AI technologies in improving the precision of cancer diagnostics within the realm of pathological anatomy.

The research contributes to the field by introducing an innovative approach that combines Ki-67 as a biomarker and AI technologies for improved diagnostic precision. The originality lies in the utilization of deep learning to calculate the percentage of labeled cells, mitigating the challenges associated with manual assessments. The validation of the model against diverse datasets and benchmarking against pathologists’ diagnoses demonstrates its superior accuracy, highlighting the value of integrating AI in pathological anatomy for enhanced diagnostic outcomes. The study represents a significant stride in original research, offering novel insights and methodologies in the pursuit of more precise cancer diagnostics.

The purpose of this paper is to design a cascaded Multilevel inverter with reduce number of switches for high power applications. This paper came up with an innovative three-phase multilevel inverter (MLI) topology, which is a cascaded structure based on classical three-legged voltage source inverter (VSI) bridges as an individual module. The prominent advantage of this topology is that it requires only one direct current (DC) link system. The main characteristic of it is that a higher number of voltage levels can be achieved with considerably a smaller number of semiconductor switches, which improves the reliability, power quality, cost and size of the system significantly.

The individual modules are cascaded through three-phase transformers to provide higher voltage at the output with the higher number of voltage levels. In this work, the phase-shifted pulse width modulation technique is implemented to verify the result.

The proposed topology is compared with three-phase cascaded H-bridge MLI (CHB-MLI) and a modified CHB-MLI topology and found better in many aspects. The proposed MLI can produce a higher number of voltage levels with fewer semiconductor switches and associated triggering circuitry. As the device count in the proposed MLI is less compared to other MLI discussed, it tends to have less switching and conduction loss which increases the efficiency and reliability. As the number of level increases, the voltage profile and the total harmonic distortion of the proposed MLI improves.

This is a transformer-based modular cascaded MLI, which is based on classical VSI bridges. Here in this topology, a single module provides all three phases. So, a single string of cascaded modules is enough for three-phase multilevel voltage generation.

The dynamics of the PV microgrid (PVMG) system are highly nonlinear and uncertain in nature. It is encountered with parametric uncertainties and disturbances. This system cannot be controlled properly by conventional linear controllers. H⁻ controller and sliding mode controller (SMC) may capable of controlling it with ease. Due to its inherent dynamics, SMC introduces unwanted chattering into the system output waveforms. This paper aims to propose a controller to reduce this chattering.

This paper presents redesign of the SMC by modifying its sliding surface and tuning its parameters by employing water-evaporation-optimization (WEO) based metaheuristic algorithm.

By using this proposed water-evaporation-optimization algorithm-double integral sliding mode controller (WEOA-DISMC), the chattering magnitude is diminished greatly. Further, to examine which controller between H8 controller and proposed WEOA-DISMC performs better in both normal and uncertain situations, a comparative analysis has been made in this paper. The considered comparison parameters are reference tracking, disturbance rejection and robust stability.

WEO tuned DISMC for PVMG system is the contribution.

Adiponectin, a bioactive molecule produced by adipose tissue, has potential effect in increasing insulin sensitivity. Adiponectin levels reduction is associated with type 2 diabetes mellitus (T2DM) and its complications, including cardiovascular disease (CVD). Triglyceride-to-high-density lipoprotein (TG:HDL) ratio can be used as a predictor of CVD risk in T2DM patients. Whiteleg shrimp (Litopenaeus vannamei) shell contains astaxanthin, macro- and micro-nutrients that may exert synergistic beneficial effects. This study aims to determine the effect of L. vannamei shell powder (LVSP) in improving adiponectin, TG, HDL and TG:HDL of T2DM Wistar rat, and to investigate the presence of any correlations between adiponectin and lipid markers.

A total of 25 male Wistar rats were divided into five equal groups: control negative [C(−)], control positive [C(+)], treatments 1, 2 and 3 (T1, T2 and T3, respectively). C(+), T1, T2 and T3 were maintained on a high-fat diet for 14 days before streptozotocin (STZ) injection. T1 and T2 groups were administered two different doses of LVSP, while T3 group was provided astaxanthin supplement (AST).

LVSP treatments significantly increase adiponectin (p =0.04) and HDL (p <0.001) but reduced TG (p <0.001) and TG:HDL (p <0.001). A higher LVSP dose was more effective in improving all markers than the lower dose; moreover, there was a comparable effect as that of AST in increasing the adiponectin levels. Strong correlations were observed between adiponectin and lipid markers.

This study shows that LVSP as a functional food, can ameliorate adiponectin levels and normalizes blood glucose levels. The LVSP reduces the risk of CVD because of the reduction of TG:HDL.

The study aims to describe the main classes of antioxidants existing in fruit, beverages, vegetables and herbs and the different extraction and application of antioxidants in food. Oxidative degradation of lipids, especially induced by reactive oxygen species, leads to quality deterioration of foods and cosmetics and could have harmful effects on health. A major challenge is to develop tools to assess the antioxidant capacity and real efficacy of these molecules. Recently, many review papers regarding antioxidants from different sources and different extraction and quantification procedures have been published. However, none of them has all the information regarding antioxidants (sources, extraction and application in food).

This paper tries to take a different perspective on antioxidants for the new researcher involved in this field.

Antioxidants from fruit, vegetables and beverages play an important role in human health, for example, preventing cancer and cardiovascular diseases and lowering the incidence of different diseases. A number of plant products act as scavengers of free radical species and so have been classified as antioxidants. Antioxidants are an important group of food additives that have the ability to protect against detrimental change of oxidizable nutrients and consequently they extend shelf-life of foods.

Most of the antioxidants present in foods are phenolic and polyphenolic compounds, but their efficacy in food for the prevention of oxidation or in the body for dealing with oxidative stress and its consequences depends on different factors.

This study collected the last finding in the field of sources and applications of natural antioxidants.